Clowder AI is a self-hosted workspace where AI agents from different model families work together as a persistent team, retaining identities, shared evidence, and memory across tasks. It is for people who want to coordinate multiple AI agents without repeatedly rebuilding their context.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zts212653/clowder-ai --skill context-self-managementgit clone --depth 1 https://github.com/zts212653/clowder-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zts212653/clowder-ai/context-self-management)<a href="https://agentmods.dev/skills/zts212653/clowder-ai/context-self-management"><img src="https://agentmods.dev/badge/skills/zts212653/clowder-ai/context-self-management.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.00898 |
| Opus 5 | $0.00023 | $0.00449 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
context-self-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Context 自管理：handoff vs 压缩是个判断 🐾
系统发来 context_management_hint(warn) = 你进了 warn 区（离 auto-seal 还有一段）。
系统知道何时该想（context% 是你的盲区，它替你盯）；干什么由你判——别一看 warn 就反射 handoff，也别无脑等压缩。
compress ≠ 坏事。干一半连贯的活、还没压过 → 压缩反而保住 in-flight 线索；这时硬 handoff 会把半成品工作态丢给一个写不全五件套的"干净自己"，更糟。
三问自检（系统给数据，你下判断）
- 线还是树？（脏=话题漂移）这一程是一条主线，还是 a→g 一堆不相关的事？
- 客观锚：
compressionCount > 0⇒ 你已经跑很久了，警惕自己低估漂移（Ragdoll尤其爱把树硬串成线）。 - 摩擦锚：同一肉身 session 连续处理多条 GitHub issue/PR、跨 repo review/tracking，且开始混淆
tracker repo/source truth repo/thread projectPath⇒ 当作树状漂移信号，进入本矩阵。
- 客观锚：
- 有干净断点吗？ 手头这件事到没到一个能利落收尾的点？干一半 = 没有。
- fill 可信度？ hint 里
fillConfidence：exact_token信那个 %；approx_token/bytes_health当弱信号；unavailable别看 %、纯靠①②自检。
2×2 决策矩阵
| 干净断点 | 干一半（中途） | |
|---|---|---|
| 脏/已压多轮 | handoff — 换干净桌子只带要紧纸条 | 冲刺模式：聚焦完成到最近断点再 handoff（warn→auto-seal 的窗口=预算） |
| 干净/没怎么压 | 续（也没必要折腾） | 压缩/续 — 保 in-flight 线索 |
怎么动手
- handoff → 调
cat_cafe_propose_session_handoff，手写五件套（做完了啥 / 正在做啥 / 下一步 / 关键决策与坑 / 别碰啥）。这是给"干净的自己"的纸条，不是给别的猫——交给别的猫是cross-cat-handoff。提案要人来 gate，你不自己封。 - 冲刺 → 不 handoff 不主动压，盯着把当前任务推到最近干净断点，到了再 handoff；真撞 auto-seal 了有 F24 兜底。
- 续/压缩 → 啥都不用做，继续干；CLI 该压会压，线索还在。
反模式：一 warn 就 handoff（丢半成品线索）/ 一 warn 就清空重来（那是焦虑不是判断）。判据永远是"线还是树 + 有没有干净断点"，不是 context% 数字本身。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 43 lines · 47 tokens per session scan A 4e57e24b5ba7
context-self-management is a skill published in the GitHub repository zts212653/clowder-ai (2,924 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 898 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.